Great Expectations Data Validation Pipeline
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as SQL databases, Spark DataFrames, and Pandas DataFrames for validation purposes. This creates a surface for indirect prompt injection where malicious instructions embedded in the data could influence the agent's behavior during validation or reporting.
- Ingestion points: External data sources including PostgreSQL, Snowflake, BigQuery, and Redshift.
- Boundary markers: None identified in the provided documentation.
- Capability inventory: SQL database connectivity, data profiling, and automated HTML report (Data Docs) generation.
- Sanitization: No specific sanitization or filtering of external data content is described in the overview.
- [METADATA_POISONING]: The
tool_ecosystemfrontmatter contains details for 'PagerDuty' and 'pdjs' (NPM package), which does not align with the skill's stated purpose of data validation using 'Great Expectations'. This appears to be a metadata inconsistency or template error rather than a malicious attempt to deceive users.
Audit Metadata